{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XCDCYN62IAVHRXGKBAVDIH2TTT","short_pith_number":"pith:XCDCYN62","schema_version":"1.0","canonical_sha256":"b8862c37da402a78dcca082a341f539cc761801019118ccc81138c9ebc85a03e","source":{"kind":"arxiv","id":"1508.03422","version":3},"attestation_state":"computed","paper":{"title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ferdous Sohel, Mohammed Bennamoun, Munawar Hayat, Roberto Togneri, Salman H. Khan","submitted_at":"2015-08-14T05:23:30Z","abstract_excerpt":"Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an under-represented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this work, we propose a cost sensitive deep neural network which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1508.03422","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-08-14T05:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"7ab6f988ad2af36c82e244d6e65138ea5f068d220013d652b67aa2131398840b","abstract_canon_sha256":"dc5e99320b933f655e94deda08fdabdb176aa8908802ad6debfbb3ec29a62731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:05.862558Z","signature_b64":"9Ys+cbpyjgPK2J4zmU6VcZuSy12D5vH8res5+INqt12DrTt4VABKH8v9AglrX3Ov2aTc1iiEG+UkfNryjObeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8862c37da402a78dcca082a341f539cc761801019118ccc81138c9ebc85a03e","last_reissued_at":"2026-05-18T00:48:05.861980Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:05.861980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ferdous Sohel, Mohammed Bennamoun, Munawar Hayat, Roberto Togneri, Salman H. Khan","submitted_at":"2015-08-14T05:23:30Z","abstract_excerpt":"Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an under-represented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this work, we propose a cost sensitive deep neural network which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03422","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1508.03422","created_at":"2026-05-18T00:48:05.862099+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.03422v3","created_at":"2026-05-18T00:48:05.862099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03422","created_at":"2026-05-18T00:48:05.862099+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCDCYN62IAVH","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCDCYN62IAVHRXGK","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCDCYN62","created_at":"2026-05-18T12:29:50.041715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11521","citing_title":"Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT","json":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT.json","graph_json":"https://pith.science/api/pith-number/XCDCYN62IAVHRXGKBAVDIH2TTT/graph.json","events_json":"https://pith.science/api/pith-number/XCDCYN62IAVHRXGKBAVDIH2TTT/events.json","paper":"https://pith.science/paper/XCDCYN62"},"agent_actions":{"view_html":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT","download_json":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT.json","view_paper":"https://pith.science/paper/XCDCYN62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.03422&json=true","fetch_graph":"https://pith.science/api/pith-number/XCDCYN62IAVHRXGKBAVDIH2TTT/graph.json","fetch_events":"https://pith.science/api/pith-number/XCDCYN62IAVHRXGKBAVDIH2TTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT/action/storage_attestation","attest_author":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT/action/author_attestation","sign_citation":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT/action/citation_signature","submit_replication":"https://pith.science/pith/XCDCYN62IAVHRXGKBAVDIH2TTT/action/replication_record"}},"created_at":"2026-05-18T00:48:05.862099+00:00","updated_at":"2026-05-18T00:48:05.862099+00:00"}